Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    msg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     payment
    -0.07
     rotation
    -0.07
     Uruguay
    -0.07
    rolls
    -0.07
     cryst
    -0.07
    Council
    -0.07
    千万别
    -0.07
     carry
    -0.06
    <Service
    -0.06
     residue
    -0.06
    POSITIVE LOGITS
    띡
    0.08
    _gateway
    0.07
    댔
    0.07
     없
    0.07
     направлен
    0.07
     gönder
    0.07
    сут
    0.07
    ~":"
    0.07
    .optional
    0.07
    _hero
    0.07
    Act Density 0.000%

    No Known Activations